Created
March 11, 2009 17:14
-
-
Save kig/77578 to your computer and use it in GitHub Desktop.
gcc -O3 -S mmul_bm.c
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| .file "mmul_bm.c" | |
| .text | |
| .p2align 4,,15 | |
| .globl mmul4x4f | |
| .type mmul4x4f, @function | |
| mmul4x4f: | |
| .LFB32: | |
| xorl %eax, %eax | |
| .L2: | |
| movss (%rsi), %xmm1 | |
| movss 4(%rsi), %xmm0 | |
| mulss (%rdi), %xmm1 | |
| mulss 16(%rdi), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss 8(%rsi), %xmm0 | |
| mulss 32(%rdi), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss 12(%rsi), %xmm0 | |
| mulss 48(%rdi), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss %xmm1, (%rdx,%rax) | |
| movss (%rsi), %xmm1 | |
| movss 4(%rsi), %xmm0 | |
| mulss 4(%rdi), %xmm1 | |
| mulss 20(%rdi), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss 8(%rsi), %xmm0 | |
| mulss 36(%rdi), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss 12(%rsi), %xmm0 | |
| mulss 52(%rdi), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss %xmm1, 4(%rdx,%rax) | |
| movss (%rsi), %xmm1 | |
| movss 4(%rsi), %xmm0 | |
| mulss 8(%rdi), %xmm1 | |
| mulss 24(%rdi), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss 8(%rsi), %xmm0 | |
| mulss 40(%rdi), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss 12(%rsi), %xmm0 | |
| mulss 56(%rdi), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss %xmm1, 8(%rdx,%rax) | |
| movss (%rsi), %xmm1 | |
| movss 4(%rsi), %xmm0 | |
| mulss 12(%rdi), %xmm1 | |
| mulss 28(%rdi), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss 8(%rsi), %xmm0 | |
| mulss 44(%rdi), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss 12(%rsi), %xmm0 | |
| mulss 60(%rdi), %xmm0 | |
| addq $16, %rsi | |
| addss %xmm0, %xmm1 | |
| movss %xmm1, 12(%rdx,%rax) | |
| addq $16, %rax | |
| cmpq $64, %rax | |
| jne .L2 | |
| rep | |
| ret | |
| .LFE32: | |
| .size mmul4x4f, .-mmul4x4f | |
| .p2align 4,,15 | |
| .globl mmul4x4d | |
| .type mmul4x4d, @function | |
| mmul4x4d: | |
| .LFB33: | |
| xorl %eax, %eax | |
| .L7: | |
| movsd (%rsi), %xmm1 | |
| movsd 8(%rsi), %xmm0 | |
| mulsd (%rdi), %xmm1 | |
| mulsd 32(%rdi), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd 16(%rsi), %xmm0 | |
| mulsd 64(%rdi), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd 24(%rsi), %xmm0 | |
| mulsd 96(%rdi), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd %xmm1, (%rdx,%rax) | |
| movsd (%rsi), %xmm1 | |
| movsd 8(%rsi), %xmm0 | |
| mulsd 8(%rdi), %xmm1 | |
| mulsd 40(%rdi), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd 16(%rsi), %xmm0 | |
| mulsd 72(%rdi), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd 24(%rsi), %xmm0 | |
| mulsd 104(%rdi), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd %xmm1, 8(%rdx,%rax) | |
| movsd (%rsi), %xmm1 | |
| movsd 8(%rsi), %xmm0 | |
| mulsd 16(%rdi), %xmm1 | |
| mulsd 48(%rdi), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd 16(%rsi), %xmm0 | |
| mulsd 80(%rdi), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd 24(%rsi), %xmm0 | |
| mulsd 112(%rdi), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd %xmm1, 16(%rdx,%rax) | |
| movsd (%rsi), %xmm1 | |
| movsd 8(%rsi), %xmm0 | |
| mulsd 24(%rdi), %xmm1 | |
| mulsd 56(%rdi), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd 16(%rsi), %xmm0 | |
| mulsd 88(%rdi), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd 24(%rsi), %xmm0 | |
| addq $32, %rsi | |
| mulsd 120(%rdi), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd %xmm1, 24(%rdx,%rax) | |
| addq $32, %rax | |
| cmpq $128, %rax | |
| jne .L7 | |
| rep | |
| ret | |
| .LFE33: | |
| .size mmul4x4d, .-mmul4x4d | |
| .section .rodata.str1.1,"aMS",@progbits,1 | |
| .LC1: | |
| .string "doubles_malloc: %f\n" | |
| .text | |
| .p2align 4,,15 | |
| .globl doubles_malloc | |
| .type doubles_malloc, @function | |
| doubles_malloc: | |
| .LFB36: | |
| pushq %r15 | |
| .LCFI0: | |
| movl $128, %edi | |
| pushq %r14 | |
| .LCFI1: | |
| pushq %r13 | |
| .LCFI2: | |
| pushq %r12 | |
| .LCFI3: | |
| pushq %rbp | |
| .LCFI4: | |
| pushq %rbx | |
| .LCFI5: | |
| subq $40, %rsp | |
| .LCFI6: | |
| call malloc | |
| movl $128, %edi | |
| movq %rax, %rbx | |
| call malloc | |
| movl $128, %edi | |
| movq %rax, 8(%rsp) | |
| call malloc | |
| movq %rax, 16(%rsp) | |
| call clock | |
| movl $0, 36(%rsp) | |
| movq %rax, 24(%rsp) | |
| .p2align 4,,10 | |
| .p2align 3 | |
| .L11: | |
| movq 8(%rsp), %r13 | |
| movq 16(%rsp), %r14 | |
| xorl %r15d, %r15d | |
| .L20: | |
| movq %r14, %rax | |
| xorl %ebp, %ebp | |
| movl $4, %r8d | |
| andl $15, %eax | |
| movsd (%r13), %xmm9 | |
| shrq $3, %rax | |
| movsd 8(%r13), %xmm8 | |
| testl %eax, %eax | |
| movsd 16(%r13), %xmm7 | |
| movsd 24(%r13), %xmm6 | |
| je .L17 | |
| movapd %xmm9, %xmm0 | |
| movl $1, %ebp | |
| movapd %xmm8, %xmm1 | |
| movl $3, %r8d | |
| mulsd (%rbx), %xmm0 | |
| mulsd 32(%rbx), %xmm1 | |
| addsd %xmm1, %xmm0 | |
| movapd %xmm7, %xmm1 | |
| mulsd 64(%rbx), %xmm1 | |
| addsd %xmm1, %xmm0 | |
| movapd %xmm6, %xmm1 | |
| mulsd 96(%rbx), %xmm1 | |
| addsd %xmm1, %xmm0 | |
| movsd %xmm0, (%r14) | |
| .L17: | |
| movl $4, %edx | |
| subl %eax, %edx | |
| movl %edx, %esi | |
| movl %edx, 32(%rsp) | |
| shrl %esi | |
| movl %esi, %r12d | |
| addl %r12d, %r12d | |
| je .L18 | |
| movapd %xmm9, %xmm0 | |
| sall $3, %eax | |
| movapd %xmm8, %xmm10 | |
| mov %eax, %eax | |
| unpcklpd %xmm0, %xmm0 | |
| leaq (%rbx,%rax), %r11 | |
| unpcklpd %xmm10, %xmm10 | |
| leaq 32(%rbx,%rax), %r10 | |
| leaq 64(%rbx,%rax), %r9 | |
| leaq 96(%rbx,%rax), %rdi | |
| leaq (%r14,%rax), %rax | |
| movapd %xmm0, %xmm5 | |
| xorl %ecx, %ecx | |
| movapd %xmm10, %xmm4 | |
| xorl %edx, %edx | |
| movapd %xmm7, %xmm0 | |
| movapd %xmm6, %xmm10 | |
| unpcklpd %xmm0, %xmm0 | |
| unpcklpd %xmm10, %xmm10 | |
| movapd %xmm0, %xmm3 | |
| movapd %xmm10, %xmm2 | |
| .L12: | |
| movsd (%r11,%rdx), %xmm0 | |
| addl $1, %ecx | |
| movsd (%r10,%rdx), %xmm10 | |
| movhpd 8(%r11,%rdx), %xmm0 | |
| movhpd 8(%r10,%rdx), %xmm10 | |
| movapd %xmm0, %xmm1 | |
| movapd %xmm10, %xmm0 | |
| movsd (%r9,%rdx), %xmm10 | |
| mulpd %xmm5, %xmm1 | |
| movhpd 8(%r9,%rdx), %xmm10 | |
| mulpd %xmm4, %xmm0 | |
| addpd %xmm0, %xmm1 | |
| movapd %xmm10, %xmm0 | |
| movsd (%rdi,%rdx), %xmm10 | |
| mulpd %xmm3, %xmm0 | |
| movhpd 8(%rdi,%rdx), %xmm10 | |
| addpd %xmm0, %xmm1 | |
| movapd %xmm10, %xmm0 | |
| mulpd %xmm2, %xmm0 | |
| addpd %xmm0, %xmm1 | |
| movapd %xmm1, (%rax,%rdx) | |
| addq $16, %rdx | |
| cmpl %esi, %ecx | |
| jb .L12 | |
| subl %r12d, %r8d | |
| addl %r12d, %ebp | |
| cmpl %r12d, 32(%rsp) | |
| je .L13 | |
| .L18: | |
| movslq %ebp,%rax | |
| leaq (%rbx,%rax,8), %rdi | |
| leaq 32(%rbx,%rax,8), %rsi | |
| leaq 64(%rbx,%rax,8), %rcx | |
| leaq 96(%rbx,%rax,8), %rdx | |
| leal (%rbp,%r15), %eax | |
| movq 16(%rsp), %rbp | |
| cltq | |
| leaq (%rbp,%rax,8), %rax | |
| .L14: | |
| movapd %xmm9, %xmm0 | |
| movapd %xmm8, %xmm1 | |
| mulsd (%rdi), %xmm0 | |
| addq $8, %rdi | |
| mulsd (%rsi), %xmm1 | |
| addq $8, %rsi | |
| addsd %xmm1, %xmm0 | |
| movapd %xmm7, %xmm1 | |
| mulsd (%rcx), %xmm1 | |
| addq $8, %rcx | |
| addsd %xmm1, %xmm0 | |
| movapd %xmm6, %xmm1 | |
| mulsd (%rdx), %xmm1 | |
| addq $8, %rdx | |
| addsd %xmm1, %xmm0 | |
| movsd %xmm0, (%rax) | |
| addq $8, %rax | |
| subl $1, %r8d | |
| jne .L14 | |
| .L13: | |
| addl $4, %r15d | |
| addq $32, %r13 | |
| addq $32, %r14 | |
| cmpl $16, %r15d | |
| jne .L20 | |
| addl $1, 36(%rsp) | |
| cmpl $10000000, 36(%rsp) | |
| jne .L11 | |
| call clock | |
| cvtsi2sdq 24(%rsp), %xmm1 | |
| cvtsi2sdq %rax, %xmm0 | |
| movl $.LC1, %edi | |
| movl $1, %eax | |
| subsd %xmm1, %xmm0 | |
| divsd .LC0(%rip), %xmm0 | |
| addq $40, %rsp | |
| popq %rbx | |
| popq %rbp | |
| popq %r12 | |
| popq %r13 | |
| popq %r14 | |
| popq %r15 | |
| jmp printf | |
| .LFE36: | |
| .size doubles_malloc, .-doubles_malloc | |
| .section .rodata.str1.1 | |
| .LC2: | |
| .string "floats_memalign: %f\n" | |
| .text | |
| .p2align 4,,15 | |
| .globl floats_memalign | |
| .type floats_memalign, @function | |
| floats_memalign: | |
| .LFB35: | |
| pushq %rbx | |
| .LCFI7: | |
| movl $64, %edx | |
| movl $16, %esi | |
| subq $32, %rsp | |
| .LCFI8: | |
| leaq 24(%rsp), %rdi | |
| call posix_memalign | |
| leaq 16(%rsp), %rdi | |
| movl $64, %edx | |
| movl $16, %esi | |
| call posix_memalign | |
| leaq 8(%rsp), %rdi | |
| movl $64, %edx | |
| movl $16, %esi | |
| call posix_memalign | |
| call clock | |
| movq 8(%rsp), %rsi | |
| movq 16(%rsp), %r8 | |
| movq %rax, %rbx | |
| movq 24(%rsp), %rdx | |
| xorl %edi, %edi | |
| .p2align 4,,10 | |
| .p2align 3 | |
| .L26: | |
| movq %r8, %rax | |
| xorl %ecx, %ecx | |
| .L25: | |
| movss (%rax), %xmm1 | |
| movss 4(%rax), %xmm0 | |
| mulss (%rdx), %xmm1 | |
| mulss 16(%rdx), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss 8(%rax), %xmm0 | |
| mulss 32(%rdx), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss 12(%rax), %xmm0 | |
| mulss 48(%rdx), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss %xmm1, (%rsi,%rcx) | |
| movss (%rax), %xmm1 | |
| movss 4(%rax), %xmm0 | |
| mulss 4(%rdx), %xmm1 | |
| mulss 20(%rdx), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss 8(%rax), %xmm0 | |
| mulss 36(%rdx), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss 12(%rax), %xmm0 | |
| mulss 52(%rdx), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss %xmm1, 4(%rsi,%rcx) | |
| movss (%rax), %xmm1 | |
| movss 4(%rax), %xmm0 | |
| mulss 8(%rdx), %xmm1 | |
| mulss 24(%rdx), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss 8(%rax), %xmm0 | |
| mulss 40(%rdx), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss 12(%rax), %xmm0 | |
| mulss 56(%rdx), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss %xmm1, 8(%rsi,%rcx) | |
| movss (%rax), %xmm1 | |
| movss 4(%rax), %xmm0 | |
| mulss 12(%rdx), %xmm1 | |
| mulss 28(%rdx), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss 8(%rax), %xmm0 | |
| mulss 44(%rdx), %xmm0 | |
| addss %xmm0, %xmm1 | |
| movss 12(%rax), %xmm0 | |
| mulss 60(%rdx), %xmm0 | |
| addq $16, %rax | |
| addss %xmm0, %xmm1 | |
| movss %xmm1, 12(%rsi,%rcx) | |
| addq $16, %rcx | |
| cmpq $64, %rcx | |
| jne .L25 | |
| addl $1, %edi | |
| cmpl $10000000, %edi | |
| jne .L26 | |
| call clock | |
| cvtsi2sdq %rbx, %xmm1 | |
| movl $.LC2, %edi | |
| cvtsi2sdq %rax, %xmm0 | |
| movl $1, %eax | |
| subsd %xmm1, %xmm0 | |
| divsd .LC0(%rip), %xmm0 | |
| call printf | |
| addq $32, %rsp | |
| popq %rbx | |
| ret | |
| .LFE35: | |
| .size floats_memalign, .-floats_memalign | |
| .section .rodata.str1.1 | |
| .LC3: | |
| .string "floats_malloc: %f\n" | |
| .text | |
| .p2align 4,,15 | |
| .globl floats_malloc | |
| .type floats_malloc, @function | |
| floats_malloc: | |
| .LFB34: | |
| pushq %r13 | |
| .LCFI9: | |
| movl $64, %edi | |
| pushq %r12 | |
| .LCFI10: | |
| pushq %rbp | |
| .LCFI11: | |
| pushq %rbx | |
| .LCFI12: | |
| subq $8, %rsp | |
| .LCFI13: | |
| call malloc | |
| movl $64, %edi | |
| movq %rax, %rbx | |
| call malloc | |
| movl $64, %edi | |
| movq %rax, %r12 | |
| call malloc | |
| movq %rax, %rbp | |
| call clock | |
| xorl %edx, %edx | |
| movq %rax, %r13 | |
| .p2align 4,,10 | |
| .p2align 3 | |
| .L31: | |
| xorl %eax, %eax | |
| .L32: | |
| movss (%r12,%rax), %xmm2 | |
| movss 4(%r12,%rax), %xmm3 | |
| movaps %xmm2, %xmm0 | |
| movaps %xmm3, %xmm1 | |
| mulss (%rbx), %xmm0 | |
| movss 8(%r12,%rax), %xmm4 | |
| mulss 16(%rbx), %xmm1 | |
| movss 12(%r12,%rax), %xmm5 | |
| addss %xmm1, %xmm0 | |
| movaps %xmm4, %xmm1 | |
| mulss 32(%rbx), %xmm1 | |
| addss %xmm1, %xmm0 | |
| movaps %xmm5, %xmm1 | |
| mulss 48(%rbx), %xmm1 | |
| addss %xmm1, %xmm0 | |
| movaps %xmm3, %xmm1 | |
| movss %xmm0, (%rbp,%rax) | |
| movaps %xmm2, %xmm0 | |
| mulss 20(%rbx), %xmm1 | |
| mulss 4(%rbx), %xmm0 | |
| addss %xmm1, %xmm0 | |
| movaps %xmm4, %xmm1 | |
| mulss 36(%rbx), %xmm1 | |
| addss %xmm1, %xmm0 | |
| movaps %xmm5, %xmm1 | |
| mulss 52(%rbx), %xmm1 | |
| addss %xmm1, %xmm0 | |
| movaps %xmm3, %xmm1 | |
| movss %xmm0, 4(%rbp,%rax) | |
| movaps %xmm2, %xmm0 | |
| mulss 24(%rbx), %xmm1 | |
| mulss 8(%rbx), %xmm0 | |
| addss %xmm1, %xmm0 | |
| movaps %xmm4, %xmm1 | |
| mulss 40(%rbx), %xmm1 | |
| addss %xmm1, %xmm0 | |
| movaps %xmm5, %xmm1 | |
| mulss 56(%rbx), %xmm1 | |
| addss %xmm1, %xmm0 | |
| movss %xmm0, 8(%rbp,%rax) | |
| mulss 12(%rbx), %xmm2 | |
| mulss 28(%rbx), %xmm3 | |
| mulss 44(%rbx), %xmm4 | |
| mulss 60(%rbx), %xmm5 | |
| addss %xmm3, %xmm2 | |
| addss %xmm4, %xmm2 | |
| addss %xmm5, %xmm2 | |
| movss %xmm2, 12(%rbp,%rax) | |
| addq $16, %rax | |
| cmpq $64, %rax | |
| jne .L32 | |
| addl $1, %edx | |
| cmpl $10000000, %edx | |
| jne .L31 | |
| call clock | |
| cvtsi2sdq %r13, %xmm1 | |
| movl $.LC3, %edi | |
| cvtsi2sdq %rax, %xmm0 | |
| movl $1, %eax | |
| subsd %xmm1, %xmm0 | |
| divsd .LC0(%rip), %xmm0 | |
| addq $8, %rsp | |
| popq %rbx | |
| popq %rbp | |
| popq %r12 | |
| popq %r13 | |
| jmp printf | |
| .LFE34: | |
| .size floats_malloc, .-floats_malloc | |
| .section .rodata.str1.1 | |
| .LC4: | |
| .string "doubles_memalign: %f\n" | |
| .text | |
| .p2align 4,,15 | |
| .globl doubles_memalign | |
| .type doubles_memalign, @function | |
| doubles_memalign: | |
| .LFB37: | |
| pushq %rbx | |
| .LCFI14: | |
| movl $128, %edx | |
| movl $16, %esi | |
| subq $32, %rsp | |
| .LCFI15: | |
| leaq 24(%rsp), %rdi | |
| call posix_memalign | |
| leaq 16(%rsp), %rdi | |
| movl $128, %edx | |
| movl $16, %esi | |
| call posix_memalign | |
| leaq 8(%rsp), %rdi | |
| movl $128, %edx | |
| movl $16, %esi | |
| call posix_memalign | |
| call clock | |
| movq 8(%rsp), %rsi | |
| movq 16(%rsp), %r8 | |
| movq %rax, %rbx | |
| movq 24(%rsp), %rdx | |
| xorl %edi, %edi | |
| .p2align 4,,10 | |
| .p2align 3 | |
| .L38: | |
| movq %r8, %rax | |
| xorl %ecx, %ecx | |
| .L37: | |
| movsd (%rax), %xmm1 | |
| movsd 8(%rax), %xmm0 | |
| mulsd (%rdx), %xmm1 | |
| mulsd 32(%rdx), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd 16(%rax), %xmm0 | |
| mulsd 64(%rdx), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd 24(%rax), %xmm0 | |
| mulsd 96(%rdx), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd %xmm1, (%rsi,%rcx) | |
| movsd (%rax), %xmm1 | |
| movsd 8(%rax), %xmm0 | |
| mulsd 8(%rdx), %xmm1 | |
| mulsd 40(%rdx), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd 16(%rax), %xmm0 | |
| mulsd 72(%rdx), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd 24(%rax), %xmm0 | |
| mulsd 104(%rdx), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd %xmm1, 8(%rsi,%rcx) | |
| movsd (%rax), %xmm1 | |
| movsd 8(%rax), %xmm0 | |
| mulsd 16(%rdx), %xmm1 | |
| mulsd 48(%rdx), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd 16(%rax), %xmm0 | |
| mulsd 80(%rdx), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd 24(%rax), %xmm0 | |
| mulsd 112(%rdx), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd %xmm1, 16(%rsi,%rcx) | |
| movsd (%rax), %xmm1 | |
| movsd 8(%rax), %xmm0 | |
| mulsd 24(%rdx), %xmm1 | |
| mulsd 56(%rdx), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd 16(%rax), %xmm0 | |
| mulsd 88(%rdx), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd 24(%rax), %xmm0 | |
| addq $32, %rax | |
| mulsd 120(%rdx), %xmm0 | |
| addsd %xmm0, %xmm1 | |
| movsd %xmm1, 24(%rsi,%rcx) | |
| addq $32, %rcx | |
| cmpq $128, %rcx | |
| jne .L37 | |
| addl $1, %edi | |
| cmpl $10000000, %edi | |
| jne .L38 | |
| call clock | |
| cvtsi2sdq %rbx, %xmm1 | |
| movl $.LC4, %edi | |
| cvtsi2sdq %rax, %xmm0 | |
| movl $1, %eax | |
| subsd %xmm1, %xmm0 | |
| divsd .LC0(%rip), %xmm0 | |
| call printf | |
| addq $32, %rsp | |
| popq %rbx | |
| ret | |
| .LFE37: | |
| .size doubles_memalign, .-doubles_memalign | |
| .p2align 4,,15 | |
| .globl main | |
| .type main, @function | |
| main: | |
| .LFB38: | |
| subq $8, %rsp | |
| .LCFI16: | |
| xorl %eax, %eax | |
| call doubles_malloc | |
| xorl %eax, %eax | |
| call doubles_memalign | |
| xorl %eax, %eax | |
| call floats_malloc | |
| xorl %eax, %eax | |
| call floats_memalign | |
| xorl %eax, %eax | |
| addq $8, %rsp | |
| ret | |
| .LFE38: | |
| .size main, .-main | |
| .section .rodata.cst8,"aM",@progbits,8 | |
| .align 8 | |
| .LC0: | |
| .long 0 | |
| .long 1093567616 | |
| .section .eh_frame,"a",@progbits | |
| .Lframe1: | |
| .long .LECIE1-.LSCIE1 | |
| .LSCIE1: | |
| .long 0x0 | |
| .byte 0x1 | |
| .string "zR" | |
| .uleb128 0x1 | |
| .sleb128 -8 | |
| .byte 0x10 | |
| .uleb128 0x1 | |
| .byte 0x3 | |
| .byte 0xc | |
| .uleb128 0x7 | |
| .uleb128 0x8 | |
| .byte 0x90 | |
| .uleb128 0x1 | |
| .align 8 | |
| .LECIE1: | |
| .LSFDE1: | |
| .long .LEFDE1-.LASFDE1 | |
| .LASFDE1: | |
| .long .LASFDE1-.Lframe1 | |
| .long .LFB32 | |
| .long .LFE32-.LFB32 | |
| .uleb128 0x0 | |
| .align 8 | |
| .LEFDE1: | |
| .LSFDE3: | |
| .long .LEFDE3-.LASFDE3 | |
| .LASFDE3: | |
| .long .LASFDE3-.Lframe1 | |
| .long .LFB33 | |
| .long .LFE33-.LFB33 | |
| .uleb128 0x0 | |
| .align 8 | |
| .LEFDE3: | |
| .LSFDE5: | |
| .long .LEFDE5-.LASFDE5 | |
| .LASFDE5: | |
| .long .LASFDE5-.Lframe1 | |
| .long .LFB36 | |
| .long .LFE36-.LFB36 | |
| .uleb128 0x0 | |
| .byte 0x4 | |
| .long .LCFI0-.LFB36 | |
| .byte 0xe | |
| .uleb128 0x10 | |
| .byte 0x4 | |
| .long .LCFI1-.LCFI0 | |
| .byte 0xe | |
| .uleb128 0x18 | |
| .byte 0x4 | |
| .long .LCFI2-.LCFI1 | |
| .byte 0xe | |
| .uleb128 0x20 | |
| .byte 0x4 | |
| .long .LCFI3-.LCFI2 | |
| .byte 0xe | |
| .uleb128 0x28 | |
| .byte 0x4 | |
| .long .LCFI4-.LCFI3 | |
| .byte 0xe | |
| .uleb128 0x30 | |
| .byte 0x4 | |
| .long .LCFI5-.LCFI4 | |
| .byte 0xe | |
| .uleb128 0x38 | |
| .byte 0x4 | |
| .long .LCFI6-.LCFI5 | |
| .byte 0xe | |
| .uleb128 0x60 | |
| .byte 0x83 | |
| .uleb128 0x7 | |
| .byte 0x86 | |
| .uleb128 0x6 | |
| .byte 0x8c | |
| .uleb128 0x5 | |
| .byte 0x8d | |
| .uleb128 0x4 | |
| .byte 0x8e | |
| .uleb128 0x3 | |
| .byte 0x8f | |
| .uleb128 0x2 | |
| .align 8 | |
| .LEFDE5: | |
| .LSFDE7: | |
| .long .LEFDE7-.LASFDE7 | |
| .LASFDE7: | |
| .long .LASFDE7-.Lframe1 | |
| .long .LFB35 | |
| .long .LFE35-.LFB35 | |
| .uleb128 0x0 | |
| .byte 0x4 | |
| .long .LCFI7-.LFB35 | |
| .byte 0xe | |
| .uleb128 0x10 | |
| .byte 0x4 | |
| .long .LCFI8-.LCFI7 | |
| .byte 0xe | |
| .uleb128 0x30 | |
| .byte 0x83 | |
| .uleb128 0x2 | |
| .align 8 | |
| .LEFDE7: | |
| .LSFDE9: | |
| .long .LEFDE9-.LASFDE9 | |
| .LASFDE9: | |
| .long .LASFDE9-.Lframe1 | |
| .long .LFB34 | |
| .long .LFE34-.LFB34 | |
| .uleb128 0x0 | |
| .byte 0x4 | |
| .long .LCFI9-.LFB34 | |
| .byte 0xe | |
| .uleb128 0x10 | |
| .byte 0x4 | |
| .long .LCFI10-.LCFI9 | |
| .byte 0xe | |
| .uleb128 0x18 | |
| .byte 0x4 | |
| .long .LCFI11-.LCFI10 | |
| .byte 0xe | |
| .uleb128 0x20 | |
| .byte 0x4 | |
| .long .LCFI12-.LCFI11 | |
| .byte 0xe | |
| .uleb128 0x28 | |
| .byte 0x4 | |
| .long .LCFI13-.LCFI12 | |
| .byte 0xe | |
| .uleb128 0x30 | |
| .byte 0x83 | |
| .uleb128 0x5 | |
| .byte 0x86 | |
| .uleb128 0x4 | |
| .byte 0x8c | |
| .uleb128 0x3 | |
| .byte 0x8d | |
| .uleb128 0x2 | |
| .align 8 | |
| .LEFDE9: | |
| .LSFDE11: | |
| .long .LEFDE11-.LASFDE11 | |
| .LASFDE11: | |
| .long .LASFDE11-.Lframe1 | |
| .long .LFB37 | |
| .long .LFE37-.LFB37 | |
| .uleb128 0x0 | |
| .byte 0x4 | |
| .long .LCFI14-.LFB37 | |
| .byte 0xe | |
| .uleb128 0x10 | |
| .byte 0x4 | |
| .long .LCFI15-.LCFI14 | |
| .byte 0xe | |
| .uleb128 0x30 | |
| .byte 0x83 | |
| .uleb128 0x2 | |
| .align 8 | |
| .LEFDE11: | |
| .LSFDE13: | |
| .long .LEFDE13-.LASFDE13 | |
| .LASFDE13: | |
| .long .LASFDE13-.Lframe1 | |
| .long .LFB38 | |
| .long .LFE38-.LFB38 | |
| .uleb128 0x0 | |
| .byte 0x4 | |
| .long .LCFI16-.LFB38 | |
| .byte 0xe | |
| .uleb128 0x10 | |
| .align 8 | |
| .LEFDE13: | |
| .ident "GCC: (GNU) 4.3.2 20081105 (Red Hat 4.3.2-7)" | |
| .section .note.GNU-stack,"",@progbits |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment